search

thepowerfuldeez / facemesh.pytorch

This is the PyTorch implementation of paper Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs (https://arxiv.org/pdf/1907.06724.pdf)
Apache License 2.0
288 stars 64 forks source link

Full img as input to model? #4

Closed zhouhuirun2015 closed 3 years ago

zhouhuirun2015 commented 3 years ago

Hi, is there a method put full img as input into model and get the right position of detections mapped into ori img?

thepowerfuldeez commented 3 years ago

Hello. You can use face detectors, e.g. dlib or https://github.com/ageitgey/face_recognition Then you should crop face with offsets and resize.

Hope I helped

zhouhuirun2015 commented 3 years ago

Thanks for your reply.